Qwen: Qwen3 4B (free)

qwen/qwen3-4b:free

Created Apr 30, 202540,960 context

$0/M input tokens$0/M output tokens

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.

Qwen: Qwen3 4B (free)

qwen/qwen3-4b:free

Created Apr 30, 202540,960 context

$0/M input tokens$0/M output tokens

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.

Recent activity on Qwen3 4B (free)

Total usage per day on OpenRouter

Prompt

4.79M

Reasoning

1.11M

Completion

520K

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.